Job description
Senior / Principal Machine Learning Engineer
Do you thrive on developing AI-driven video systems for real-time? Are you excited by the challenge of enhancing performance on resource-limited devices? We are looking for a Senior or Principal Machine Learning Engineer to play a vital role in advancing next-generation technology.
About the Position As part of our real-time AI video processing team, you’ll contribute to building high-efficiency AI and video pipelines designed for use in operating rooms. This role requires expertise in real-time video computation, parallel processing, and the ability to work in a multidisciplinary environment alongside researchers, software engineers, and designers.
Your Responsibilities
✔ Degree in Computer Science, Software Engineering, or a related technical discipline
✔ Expertise in TensorFlow or PyTorch
✔ Knowledge of ML optimization techniques such as quantization, model pruning, and knowledge distillation
✔ Experience developing with CUDA or OpenCL
✔ Proficiency in TensorRT, ONNX, and hardware-accelerated inference
✔ Strong troubleshooting and problem-solving abilities
✔ Ability to create clear, well-structured, and maintainable code
✔ Comfortable working independently and taking ownership of development projects
Do you thrive on developing AI-driven video systems for real-time? Are you excited by the challenge of enhancing performance on resource-limited devices? We are looking for a Senior or Principal Machine Learning Engineer to play a vital role in advancing next-generation technology.
About the Position As part of our real-time AI video processing team, you’ll contribute to building high-efficiency AI and video pipelines designed for use in operating rooms. This role requires expertise in real-time video computation, parallel processing, and the ability to work in a multidisciplinary environment alongside researchers, software engineers, and designers.
Your Responsibilities
- Deploy deep learning model results from the ML team into real-time video systems.
- Design and refine AI inference pipelines for high-speed processing on compact hardware.
- Create optimized CUDA kernels for enhanced video and AI performance.
- Work alongside cross-functional teams to seamlessly integrate machine learning solutions into products.
- Follow best practices to develop secure and robust software for medical applications.
- Maintain high coding standards through rigorous testing and peer reviews.
✔ Degree in Computer Science, Software Engineering, or a related technical discipline
✔ Expertise in TensorFlow or PyTorch
✔ Knowledge of ML optimization techniques such as quantization, model pruning, and knowledge distillation
✔ Experience developing with CUDA or OpenCL
✔ Proficiency in TensorRT, ONNX, and hardware-accelerated inference
✔ Strong troubleshooting and problem-solving abilities
✔ Ability to create clear, well-structured, and maintainable code
✔ Comfortable working independently and taking ownership of development projects